Indian Journal of Public Health Research & Development
  • Year: 2018
  • Volume: 9
  • Issue: 8

Analysis of translation invariant wavelet transform for epileptic seizure detection using support vector machine

1Research Scholar, Hindustan Institute of Technology and Science, Padur, Chennai

2Associate Professor, Hindustan Institute of Technology and Science, Padur, Chennai

*Corresponding Author: Vallikannu R, Associate Professor, Hindustan Institute of Technology and Science, Padur, Chennai. Email: vallikannu@hindustanuniv.ac.in

Online published on 21 September, 2018.

Abstract

Electroencephalogram (EEG) signal of human provide important information about the changes in the brain. Based on the information, epileptic seizure can be easily identified. In this paper, Translation Invariant Wavelet Transform (TIWT) based EEG signal classification is presented. At first, signals are represented by TIWT to extract information. TIWT representation of EEG signal produces Low Frequency Band (LFB) and High Frequency Band (HFB). From LFB and HFB features are extracted and Support Vector Machine (SVM) classifier evaluates them into either Normal Signal (NS) or Epileptic Signal (ES). Experimental results prove that TIWT representation of EEG signals provides average classification accuracy of 97.5% at 3rd level representation.

Keywords

Epileptic seizure, brain disorder, EEG, translation invariant wavelet, SVM classifier